{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:S526QSSWUOH4ZYNSBIM73G6RI5","short_pith_number":"pith:S526QSSW","canonical_record":{"source":{"id":"1906.12158","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-28T12:23:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1c06c86fbd7e9e45578029c5a7e23d18bf696da7d975fdb4d8c8bf6d5aac184d","abstract_canon_sha256":"0112bc71819e8636510daa695e5b69baa4b0bc003860d0a4a7e5da589e3d6ef5"},"schema_version":"1.0"},"canonical_sha256":"9775e84a56a38fcce1b20a19fd9bd147418bcb21a45ba8f52918ea42b8ccd23c","source":{"kind":"arxiv","id":"1906.12158","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.12158","created_at":"2026-05-17T23:41:59Z"},{"alias_kind":"arxiv_version","alias_value":"1906.12158v1","created_at":"2026-05-17T23:41:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.12158","created_at":"2026-05-17T23:41:59Z"},{"alias_kind":"pith_short_12","alias_value":"S526QSSWUOH4","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"S526QSSWUOH4ZYNS","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"S526QSSW","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:S526QSSWUOH4ZYNSBIM73G6RI5","target":"record","payload":{"canonical_record":{"source":{"id":"1906.12158","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-28T12:23:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1c06c86fbd7e9e45578029c5a7e23d18bf696da7d975fdb4d8c8bf6d5aac184d","abstract_canon_sha256":"0112bc71819e8636510daa695e5b69baa4b0bc003860d0a4a7e5da589e3d6ef5"},"schema_version":"1.0"},"canonical_sha256":"9775e84a56a38fcce1b20a19fd9bd147418bcb21a45ba8f52918ea42b8ccd23c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:59.118755Z","signature_b64":"ODdJUH6+fIR7qzgQwlHZOUTsgKSy7UqhklmCnVFbF7F8juZAfF00qu8UhuUlliNKPmA2wWa91bd1B9WpbEYhAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9775e84a56a38fcce1b20a19fd9bd147418bcb21a45ba8f52918ea42b8ccd23c","last_reissued_at":"2026-05-17T23:41:59.118340Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:59.118340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.12158","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:41:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aIfldd0DOPPfNPUNuCksuCoX3wJQSPvcFqh9HNVe933xZ7MlSJa5wh6tlaVkQJOd7gXXYnkO2DLAK7ds0pupCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T04:59:50.782647Z"},"content_sha256":"e9191da3f16831b04e155fab005d67b36cb731ea785ff0e5eb6b0e4a8fadbce9","schema_version":"1.0","event_id":"sha256:e9191da3f16831b04e155fab005d67b36cb731ea785ff0e5eb6b0e4a8fadbce9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:S526QSSWUOH4ZYNSBIM73G6RI5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Open-Ended Long-Form Video Question Answering via Hierarchical Convolutional Self-Attention Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jingkuan Song, Xiaofei He, Zhijie Lin, Zhou Zhao, Zhu Zhang","submitted_at":"2019-06-28T12:23:37Z","abstract_excerpt":"Open-ended video question answering aims to automatically generate the natural-language answer from referenced video contents according to the given question. Currently, most existing approaches focus on short-form video question answering with multi-modal recurrent encoder-decoder networks. Although these works have achieved promising performance, they may still be ineffectively applied to long-form video question answering due to the lack of long-range dependency modeling and the suffering from the heavy computational cost. To tackle these problems, we propose a fast Hierarchical Convolution"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.12158","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:41:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6XbMdtT81zJaC8RW8xZls60G4tfkc2auQ+tTIJXknq4Ff2GEbXdr5k6dkJFufRIdEsVQ7nqTlRfVz/fa47BrBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T04:59:50.783007Z"},"content_sha256":"e4baece405eb28d15b829318472c8351a397e504a1dd1c192939b00ca866888d","schema_version":"1.0","event_id":"sha256:e4baece405eb28d15b829318472c8351a397e504a1dd1c192939b00ca866888d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S526QSSWUOH4ZYNSBIM73G6RI5/bundle.json","state_url":"https://pith.science/pith/S526QSSWUOH4ZYNSBIM73G6RI5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S526QSSWUOH4ZYNSBIM73G6RI5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-01T04:59:50Z","links":{"resolver":"https://pith.science/pith/S526QSSWUOH4ZYNSBIM73G6RI5","bundle":"https://pith.science/pith/S526QSSWUOH4ZYNSBIM73G6RI5/bundle.json","state":"https://pith.science/pith/S526QSSWUOH4ZYNSBIM73G6RI5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S526QSSWUOH4ZYNSBIM73G6RI5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:S526QSSWUOH4ZYNSBIM73G6RI5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0112bc71819e8636510daa695e5b69baa4b0bc003860d0a4a7e5da589e3d6ef5","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-28T12:23:37Z","title_canon_sha256":"1c06c86fbd7e9e45578029c5a7e23d18bf696da7d975fdb4d8c8bf6d5aac184d"},"schema_version":"1.0","source":{"id":"1906.12158","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.12158","created_at":"2026-05-17T23:41:59Z"},{"alias_kind":"arxiv_version","alias_value":"1906.12158v1","created_at":"2026-05-17T23:41:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.12158","created_at":"2026-05-17T23:41:59Z"},{"alias_kind":"pith_short_12","alias_value":"S526QSSWUOH4","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"S526QSSWUOH4ZYNS","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"S526QSSW","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:e4baece405eb28d15b829318472c8351a397e504a1dd1c192939b00ca866888d","target":"graph","created_at":"2026-05-17T23:41:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Open-ended video question answering aims to automatically generate the natural-language answer from referenced video contents according to the given question. Currently, most existing approaches focus on short-form video question answering with multi-modal recurrent encoder-decoder networks. Although these works have achieved promising performance, they may still be ineffectively applied to long-form video question answering due to the lack of long-range dependency modeling and the suffering from the heavy computational cost. To tackle these problems, we propose a fast Hierarchical Convolution","authors_text":"Jingkuan Song, Xiaofei He, Zhijie Lin, Zhou Zhao, Zhu Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-28T12:23:37Z","title":"Open-Ended Long-Form Video Question Answering via Hierarchical Convolutional Self-Attention Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.12158","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e9191da3f16831b04e155fab005d67b36cb731ea785ff0e5eb6b0e4a8fadbce9","target":"record","created_at":"2026-05-17T23:41:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0112bc71819e8636510daa695e5b69baa4b0bc003860d0a4a7e5da589e3d6ef5","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-28T12:23:37Z","title_canon_sha256":"1c06c86fbd7e9e45578029c5a7e23d18bf696da7d975fdb4d8c8bf6d5aac184d"},"schema_version":"1.0","source":{"id":"1906.12158","kind":"arxiv","version":1}},"canonical_sha256":"9775e84a56a38fcce1b20a19fd9bd147418bcb21a45ba8f52918ea42b8ccd23c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9775e84a56a38fcce1b20a19fd9bd147418bcb21a45ba8f52918ea42b8ccd23c","first_computed_at":"2026-05-17T23:41:59.118340Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:59.118340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ODdJUH6+fIR7qzgQwlHZOUTsgKSy7UqhklmCnVFbF7F8juZAfF00qu8UhuUlliNKPmA2wWa91bd1B9WpbEYhAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:59.118755Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.12158","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9191da3f16831b04e155fab005d67b36cb731ea785ff0e5eb6b0e4a8fadbce9","sha256:e4baece405eb28d15b829318472c8351a397e504a1dd1c192939b00ca866888d"],"state_sha256":"fd8635571fbcfb86f3151664eef338b6ab9b1adef42c3ef434596ae9001d43a5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dL0D1vH+FWiEFA1W/Fos8HMmfnrFnDOJX3Aen2/N6t2Qm8YxDfVCJJYAN1fG0dcTCcc8hkhHno5cNOxSO8vUBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T04:59:50.785199Z","bundle_sha256":"36e354e5bad412f0070641e3d6a99ea8a8a38614baf0d762d4cd94614f3df4eb"}}